DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

📖 [译] scikit-learn（sklearn） 中文文档

Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。

Implementation of Graph Convolutional Networks in TensorFlow

GPT2 for Multiple Languages, including pretrained models. GPT2 多语言支持, 15亿参数中文预训练模型

State-of-the-Art Embeddings, Retrieval, and Reranking

Hyperbolic Knowledge Graph embeddings.

Google Research

BERT as language model, fork from https://github.com/google-research/bert

Open Chinese Language Pre-trained Model Zoo

General purpose unsupervised sentence representations

EmbedRank: Unsupervised Keyphrase Extraction using Sentence Embeddings (official implementation)

wtfpython的中文翻译/持续🚧.../ 能力有限，欢迎帮我改进翻译

Tensorflow solution of NER task Using BiLSTM-CRF model with Google BERT Fine-tuning And private Server services

Java library and command-line application for converting Scikit-Learn pipelines to PMML

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Aspect Based Sentiment Analysis, PyTorch Implementations. 基于方面的情感分析，使用PyTorch实现。

Code for acl2017 paper "An unsupervised neural attention model for aspect extraction"

TensorFlow code and pre-trained models for BERT

Chinese NER using Lattice LSTM. Code for ACL 2018 paper.

CRFsuite with partial annotation. Used in our paper 'Domain adaptation for CRF-based Chinese word segmentation using free annotations'

Chinese NER using Lattice LSTM. Code for ACL 2018 paper.

中文自然语言处理工具包 Toolkit for Chinese natural language processing

CRF++-0.58 extended with a few stochastic gradient based optimization routines

ansj分词.ict的真正java实现.分词效果速度都超过开源版的ict. 中文分词,人名识别,词性标注,用户自定义词典